- Title
- A study on environmental issues of blasting using advanced support vector machine algorithms
- Creator
- Chen, Lihua; Armaghani, Danial; Fakharian, Pouyan; Bhatawdekar, Ramesh; Samui, P.; Khandelwal, Manoj; Khedher, Khaled
- Date
- 2022
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/188167
- Identifier
- vital:17222
- Identifier
-
https://doi.org/10.1007/s13762-022-03999-y
- Identifier
- ISSN:1735-1472 (ISSN)
- Abstract
- Air overpressure is a critical negative effect of blasting in construction or production sites and projects. So far, many attempts have been made to prevent or reduce this negative effect on the nearby construction, equipment, or people. While various experiential equations have been proposed to forecast the air overpressure value for determining the blasting area, these models are typically inaccurate and impractical. Due to the recent efforts to predict the air overpressure by employing artificial intelligence techniques, this study developed five support vector machine-based models optimized by some praised optimization techniques, including the moth flame optimization, particle swarm optimization, grey wolf optimization, cuckoo optimization algorithm, and whale optimization algorithm. These algorithms optimize the most important parameters of the support vector machine, including “C” and “gamma”, and improve the performance of this model for air overpressure prediction. The findings showed that the moth flame optimization algorithm is the best optimizer for support vector machine and is suitable for air overpressure prediction. The support vector machine–moth flame optimization model achieved the best R2 (train: 0.9939; test: 0.9941) and comprehensive score (34). On the other hand, the worst model was the support vector machine–particle swarm optimization, which achieved the lowest comprehensive score (13). In addition, all optimization techniques improved the performance of the single support vector machine model. The findings of this study imply that all optimization techniques successfully enhanced the performance of the support vector machine model; however, the moth flame optimization optimizer was the most effective one. The support vector machine–moth flame optimization technique can be employed to solve other mining-related issues. © 2022, Islamic Azad University (IAU). Correction to: A study on environmental issues of blasting using advanced support vector machine algorithms (International Journal of Environmental Science and Technology, (2022), 19, 7, (6221-6240), 10.1007/s13762-022-03999-y): The original version of this article unfortunately contains two mistakes. The spelling of the third author's name was incorrect. The correct name is Pouyan Fakharian (P. Fakharian). Another error was in the acknowledgment section. The correct Grant No. is KJQN202103415. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2022
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Relation
- International Journal of Environmental Science and Technology Vol. 19, no. 7 (2022), p. 6221-6240
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright © 2022, Islamic Azad University (IAU)
- Rights
- Open Access
- Subject
- MD Multidisciplinary; Blasting air overpressure; Metaheuristic techniques; Prediction and minimization; Support vector machine; SVM-based optimization techniques
- Full Text
- Reviewed
- Funder
- Supported by the Science and Technology Research Program of Chongqing Municipal Education Commission (Grant No. JQN202103415).
- Hits: 752
- Visitors: 724
- Downloads: 53
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE2 | Accepted version | 2 MB | Adobe Acrobat PDF | View Details Download |